AvailableAnthropicChatCache 90% off
claude-sonnet-5

Build next-gen apps with claude-sonnet-5

API Code Example

Pricing

Official Price

Input$3.00
Output$15.00
Per 1M Tokens

TokenLab Price

Input$1.95
Output$9.75
Per 1M Tokens
Pricing Details
Per 1M Tokens
Pricing Tiers
Spec
Input Official $3.00/1M tokens · Platform $1.95/1M tokens Output Official $15.00/1M tokens · Platform $9.75/1M tokens Cache Read Official $0.30/1M tokens · Platform $0.195/1M tokens Cache Creation Official $3.75/1M tokens · Platform $2.44/1M tokens Cache Creation (1h) Official $6.00/1M tokens · Platform $3.90/1M tokens
Pinned to Anthropic's standard pricing scheduled for September 1, 2026: $3 input / $15 output, cache read $0.30, cache creation $3.75 (5m) / $6.00 (1h) per 1M tokens. The temporary $2/$10 introductory window is intentionally not selected so TokenLab cannot undercharge after the transition.

One-click test

Sign in once and Web Agent keeps this model, prompt, and request preset for you.

Test claude-sonnet-5 in Web Agent with a short request at /v1/messages, then show request body, latency, and response.

API workbench

The default route for production. The code sample below uses this endpoint with the format you pick.

ChatOpenAI Compatible
POST/v1/messages
API Format:
curl https://api.tokenlab.sh/v1/messages \
  -H "Content-Type: application/json" \
  -H "x-api-key: sk-xxx" \
  -H "anthropic-version: 2023-06-01" \
  -d '{
    "model": "claude-sonnet-5",
    "max_tokens": 1024,
    "messages": [
      {"role": "user", "content": "Hello!"}
    ]
  }'

Use cases

Best for

Reasoning

Multi-step reasoning, analysis, and research workflows

Vision

Reading images, parsing documents, and answering visual questions

01

Agents and tools

Drive reasoning, support triage, tool calls, and multi-step task flows.

02

Developer workflows

Generate, review, or debug code without rewiring your stack.

03

Knowledge assistants

Ship chat, search, and retrieval with predictable cost and behavior.

04

Side-by-side test

Compare real response quality, latency, and price for production defaults.

Prompt examples

Write a concise support reply and list the assumptions behind it.

Review this API design and call out the top three integration risks.

Turn a long changelog into release notes a non-engineer would read.

This model has conditional pricing. Monthly token totals alone cannot produce a reliable estimate; use the detailed pricing for the request specification, cache, and applicable time window.

FAQ

How much does claude-sonnet-5 cost?

On TokenLab, claude-sonnet-5 costs Input $1.95 / Output $9.75 Per 1M Tokens. The pricing table above shows the full breakdown. Rates depend on the billing unit, specification, and usage. Compare matching conditions in the model's detailed pricing; a single rate does not determine the total cost.

What is claude-sonnet-5 best for?

claude-sonnet-5 is a strong fit for JSON Mode, Prompt Cache, Reasoning. You can call it through TokenLab with one API key.

How do I call the claude-sonnet-5 API?

Get a TokenLab API key, then send your request to https://api.tokenlab.sh/v1/messages. The API workbench above has a recommended endpoint and copy-ready code.

Which endpoint should claude-sonnet-5 use?

Use https://api.tokenlab.sh/v1/messages as the default for claude-sonnet-5. If a provider-native format is supported, the API workbench shows that endpoint too.

Can I test claude-sonnet-5 before integrating it?

Yes. Try in Web Agent opens a ready test for claude-sonnet-5 and keeps your prompt after sign-in, so you don’t lose context.

Related Models